{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:50:37Z","timestamp":1782406237622,"version":"3.54.5"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209879","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-7","source":"Crossref","is-referenced-by-count":1,"title":["THOR: Text to Human-Object Interaction Diffusion via Relation Intervention"],"prefix":"10.1109","author":[{"given":"Qianyang","family":"Wu","sequence":"first","affiliation":[{"name":"ShanghaiTech University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoshui","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Xu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Yu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingya","family":"Wang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1692","article-title":"One transformer fits all distributions in multi-modal diffusion at scale","volume-title":"International Conference on Machine Learning","author":"Bao"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00096"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14739"},{"key":"ref7","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref8","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref9","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref15","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01246"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00458"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01451"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00462"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3606931"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201315"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01880"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_4"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00271"},{"key":"ref29","article-title":"Interdreamer: Zero-shot text to 3d dynamic human-object interaction","author":"Xu","year":"2024"},{"key":"ref30","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3D classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209879.pdf?arnumber=11209879","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:59:24Z","timestamp":1761890364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209879\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209879","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}